This study aims at reviewing whether regional and generational differences exist in behavior intention to adopt low-carbon travel modes. Based on 759 questionnaires collected from three cities (Zhenjiang, Suzhou, and Shanghai) with different population sizes in China, we develop a modified theory of planned behavior (MTPB) model framework integrating low-carbon transport policies, psychological aspects, personal norms, and travel habits. A more advanced partial least-square method of structural equation model (PLS-SEM) and a multiple-group analysis (MGA) model are applied to estimate the effects and heterogeneities of these factors on low-carbon travel behavior intention among three cities and four age groups. The results show that the roles of low-carbon policies, subjective norms, and personal norms on behavior intention of adopting low-carbon travel modes are more salient. The effect of low-carbon policy on behavior is much weaker than it is on intention, and it does not follow that such intention will often be followed up with action. There is regional and generational heterogeneity in terms of the influence on low-carbon travel behavior intention. In particular, the benefits of low-carbon policies are more remarkable in the middle-sized city, young adult group, and pre-older adult group. The low-carbon travel behavior intention in the large-sized city, junior-middle adult group, and senior-middle adult group are affected by subjective norms more easily. The large-sized city and young adult group have better personal norms in favor of low-carbon travel. The findings could provide helpful insights into developing heterogeneous transport policies to encourage different travelers to switch from auto to low-carbon travel modes.

Due to poor road design, challenging terrain, and difficult geological conditions, traffic accidents on mountainous two-lane roads are more frequent and severe. This study aims to address the lack of understanding of key factors affecting accident severity with the goal of improving mountainous traffic safety, thereby contributing to sustainable transportation systems. The focus of this study is to compare the interpretability of model performances with three statistical models (Ordered Logit, Partial Proportional Odds Model, and Multinomial Logit) and six machine learning models (Decision Tree, Random Forest, Gradient Boosting, Extra Trees, AdaBoost, and XGBoost) on two-lane mountain roads in Yunnan Province, China. Additionally, we assessed the ability of these models to uncover underlying causal relationships, particularly how accident causes affect severity. Using the SHapley Additive exPlanations (SHAP) method, we interpreted the influence of risk factors in the machine learning models. Our findings indicate that machine learning models, especially XGBoost, outperform statistical models in predicting accident severity. The results highlight that accident patterns are the most significant determinants of severity, followed by road-related factors and the type of colliding vehicles. Environmental factors like weather, however, have minimal impact. Notably, vehicle falling, head-on collisions, and longitudinal slope sections are linked to more severe accidents, while minor accidents are more frequent on horizontal curve sections and areas that combine curves and slopes. These insights can help traffic management agencies develop targeted measures to reduce accident rates and enhance road safety, which is critical for promoting sustainable transportation in mountainous regions.